Rail vehicle positioning method and device, electronic device, readable storage medium

Abstract

The present disclosure provides a method and device for positioning a rail vehicle, an electronic device, and a readable storage medium, belonging to the technical field of rail vehicle positioning. The method includes: constructing a rail map; determining the driving trajectory of the rail vehicle on the rail map based on the acceleration data and angular velocity data of the rail vehicle; and determining the position of the rail vehicle based on the driving trajectory of the rail vehicle on the rail map. The method and device for positioning a rail vehicle, the electronic device, and the readable storage medium provided by the present disclosure can improve the positioning accuracy of the rail vehicle in a tunnel.

Description

Technical Field

[0001] This disclosure belongs to the technical field of rail vehicle positioning. More specifically, it relates to a rail vehicle positioning method and device, an electronic device, and a readable storage medium. Background Art

[0002] In the field of tunnel construction, the accurate positioning of rail vehicles is crucial. Traditional rail vehicle positioning technologies have exposed many deficiencies when facing the complex environment of multiple rails and turnouts in tunnels. Some methods that rely on external signal sources (such as GPS) cannot work effectively due to the shielding and attenuation of signals by the tunnel. The methods based on manual observation or landmark recognition are limited by factors such as light, vision, and manpower, with low efficiency and difficult to guarantee accuracy, and it is difficult to meet the requirements of real-time and accurate scheduling of rail vehicles during construction. With the development of tunnel construction technology towards high efficiency and automation, there is an urgent need for a new positioning method. Summary of the Invention

[0003] The purpose of this disclosure is to provide a rail vehicle positioning method and device, an electronic device, and a readable storage medium to improve the positioning accuracy of rail vehicles in tunnels.

[0004] In the first aspect of the embodiments of this disclosure, a rail vehicle positioning method is provided, including:

[0005] Construct a rail map;

[0006] Determine the driving trajectory of the rail vehicle on the rail map based on the acceleration data and angular velocity data of the rail vehicle;

[0007] Determine the position of the rail vehicle based on the driving trajectory of the rail vehicle on the rail map.

[0008] In the second aspect of the embodiments of this disclosure, a rail vehicle positioning device is provided, including:

[0009] A rail map construction module for constructing a rail map;

[0010] A driving trajectory generation module for determining the driving trajectory of the rail vehicle on the rail map based on the acceleration data and angular velocity data of the rail vehicle;

[0011] A positioning module for determining the position of the rail vehicle based on the driving trajectory of the rail vehicle on the rail map.

[0012] In the third aspect of the embodiments of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned rail vehicle positioning method are implemented.

[0013] In the fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned rail vehicle positioning method are implemented.

[0014] The beneficial effects of the rail vehicle positioning method, device, electronic device, and readable storage medium provided by the embodiments of the present disclosure are as follows: First, by constructing a rail map, the embodiments of the present disclosure provide an accurate reference benchmark for the real-time positioning of the rail vehicle, making the positioning process more intuitive and reliable. Second, using acceleration data and angular velocity data to determine the driving trajectory of the rail vehicle not only has high dynamic adaptability but can also accurately capture changes in the motion state of the rail vehicle, thereby ensuring the accuracy of the driving trajectory. Finally, matching the driving trajectory with the rail map enables the rapid and accurate determination of the position of the rail vehicle. This not only improves the positioning efficiency but also enhances the accuracy and stability of the rail vehicle positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart showing the rail vehicle positioning method provided by an embodiment of the present disclosure;

[0017] Figure 2 It is a block diagram showing the structure of the rail vehicle positioning device provided by an embodiment of the present disclosure;

[0018] Figure 3 It is a schematic block diagram showing the electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0020] To make the purpose, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments with reference to the drawings.

[0021] During the tunnel construction process, multiple railway tracks are often laid to meet the needs of material transportation, personnel deployment, and the transfer of construction equipment, etc. As an important transportation tool in tunnel construction, the accurate positioning of the rail vehicle is of crucial significance for the efficient and safe progress of the construction. Due to the complex internal environment of the tunnel and poor communication conditions, traditional rail vehicle positioning methods have limitations in such a complex tunnel track environment. Therefore, this embodiment discloses a rail vehicle positioning method, device, electronic device, and readable storage medium.

[0022] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of the rail vehicle positioning method provided by an embodiment of the present disclosure. The method includes:

[0023] S101: Construct a track map.

[0024] In this embodiment, detailed spatial information of the railway tracks and the surrounding environment within the entire tunnel can be obtained through 3D laser scanning technology to construct a 3D point cloud model; feature extraction is performed based on the 3D point cloud model to obtain the geometric features of the railway tracks and turnouts; and a track map containing railway track and turnout information is generated based on the geometric features of the railway tracks and turnouts.

[0025] In the track map, different railway tracks can be represented by corresponding lines, and key nodes such as turnouts can be marked with specific symbols or identifiers. Each railway track can be assigned a unique number for distinction, and the turnout can have a corresponding identification number and indication information of its switchable tracks, making the entire track map an important reference basis for rail vehicle positioning, clearly and intuitively showing all the paths and key position relationships of the rail vehicle's operation.

[0026] S102: Determine the driving trajectory of the rail vehicle on the track map based on the acceleration data and angular velocity data of the rail vehicle.

[0027] In this embodiment, an acceleration sensor and an angular velocity sensor can be installed on the rail vehicle. Among them, the acceleration data is the data obtained by the acceleration sensor, and the angular velocity data is the data obtained by the angular velocity sensor.

[0028] The acceleration sensor and the angular velocity sensor can continuously obtain the acceleration change situation of the rail vehicle during operation and the rotational angular velocity situation of the vehicle body.

[0029] In this embodiment, the first raw data of the acceleration sensor is obtained, and the second raw data of the angular velocity sensor is obtained; the first raw data and the second raw data are respectively preprocessed to obtain the acceleration data and the angular velocity data.

[0030] The first and second original data obtained contain certain noise and errors, and data preprocessing needs to be carried out first. For example, a filtering algorithm is used to remove high-frequency noise interference, and outliers are identified and corrected to ensure that the data on which subsequent analysis is based is relatively accurate and reliable.

[0031] In this embodiment, displacement information of the rail vehicle can be obtained based on acceleration data, and steering characteristic information of the rail vehicle (such as the steering angle and steering time of the rail vehicle, etc.) can be obtained based on angular velocity data.

[0032] Starting from the initial known position of the rail vehicle (such as the known coordinate position starting from a specific rail starting point), according to the continuously updated speed, displacement, and steering information, the driving trajectory of the rail vehicle in the time series is gradually drawn.

[0033] During the drawing process, it is necessary to continuously refer to the constructed rail map, and judge which specific rail the rail vehicle is currently traveling along according to the characteristics of the rail, such as the direction and curvature. When passing through a turnout position, it is possible to determine whether the rail vehicle has switched to another connected rail by the sudden change of acceleration and angular velocity and the matching with the turnout switching logic, and then accurately construct a complete and practical driving trajectory within the framework of the rail map.

[0034] S103: Determine the position of the rail vehicle based on the driving trajectory of the rail vehicle on the rail map.

[0035] In this embodiment, the driving trajectory of the rail vehicle is matched and compared with the rail map to determine the position of the rail vehicle.

[0036] The range of the rail line that matches it can be screened out from the rail map through the overall trend of the driving trajectory and each key node passed (such as turnouts with specific numbers, intersections of different rails, etc.). For example, if the trajectory shows that the rail vehicle has passed through several turnouts with specific identifications, and the trend and the order of passing through these turnouts are consistent with the trend of a certain rail on the map, the rail where the rail vehicle is located and its specific position on that rail can be locked.

[0037] Exemplarily, it is assumed that in a certain tunnel construction, the rail vehicle starts from the rail starting point A, and the starting coordinate is (0,0). The rail map is constructed through three-dimensional laser scanning, where the number of rail 1 is T1, the number of rail 2 is T2, and the number of turnout 1 is S1, connecting T1 and T2.

[0038] After the rail vehicle starts, the acceleration sensor and the angular velocity sensor start to work. After obtaining the raw data and preprocessing it, acceleration data and angular velocity data are obtained. The speed is calculated by integrating the acceleration data, and the displacement is obtained by integrating again. The steering is determined in combination with the angular velocity. For example, the rail vehicle first travels in a straight line for a certain distance, the displacement reaches 100 meters and there is no steering. According to the rail map, it is still on the T1 rail.

[0039] When approaching the turnout S1, the sensor data suddenly changes. The changes in acceleration and angular velocity conform to the logic of switching from T1 to T2. So it is determined that the rail vehicle switches to the T2 rail. Continue to draw the trajectory according to the subsequent displacement and steering information. When the trajectory shows that the rail vehicle has passed a specific identification turnout again and the direction conforms to the subsequent branch track of T2, it is finally determined that the rail vehicle is at a certain position on the T2 rail, such as 50 meters away from a certain intersection point. In this way, the rail vehicle is accurately positioned during the entire construction process, ensuring the orderly progress of tunnel construction.

[0040] It can be concluded from the above that in this embodiment, first, by constructing a rail map, a precise reference benchmark is provided for the real-time positioning of the rail vehicle, making the positioning process more intuitive and reliable. Second, using the acceleration data and angular velocity data to determine the driving trajectory of the rail vehicle not only has a high degree of dynamic adaptability but can also accurately capture the changes in the motion state of the rail vehicle, thus ensuring the accuracy of the driving trajectory. Finally, matching the driving trajectory with the rail map realizes the rapid and accurate determination of the position of the rail vehicle. This not only improves the positioning efficiency but also enhances the accuracy and stability of the rail vehicle positioning.

[0041] In an embodiment of the present disclosure, determining the driving trajectory of a rail vehicle on a rail map based on the acceleration data and angular velocity data of the rail vehicle includes:

[0042] Processing the acceleration data to obtain the vibration characteristic data of the rail vehicle;

[0043] Processing the angular velocity data to obtain the steering characteristic data of the rail vehicle;

[0044] Determining the driving trajectory of the rail vehicle based on the vibration characteristic data and the steering characteristic data;

[0045] Matching the driving trajectory of the rail vehicle with the rail map to obtain the driving trajectory of the rail vehicle on the rail map.

[0046] In this embodiment, the acceleration data can be subjected to a fast Fourier transform to obtain the vibration characteristic data of the rail vehicle.

[0047] The Fast Fourier Transform can convert the acceleration signal in the time domain into a frequency domain signal, thereby obtaining the intensity distribution of different frequency components. The vibrations of the rail vehicle during driving may come from various factors, such as track irregularities, wheel non-roundness, mechanical vibrations of the vehicle itself, etc. These vibrations exhibit specific frequency peaks or frequency bands in the frequency domain. For example, the periodic irregularities of the track may result in a strong vibration signal at a certain fixed frequency. By identifying these characteristic frequencies and the corresponding vibration amplitudes, the vibration characteristic data of the rail vehicle can be obtained.

[0048] In this embodiment, the angular velocity data can be integrated to obtain the attitude angle data of the rail vehicle. By analyzing the amplitude and frequency of the attitude angle change, the steering characteristic data can be extracted.

[0049] When the rail vehicle turns, the angular velocity of the rail vehicle will change significantly, and the integrated attitude angle will also change accordingly. By observing information such as the rate of change of the attitude angle, the duration of the turn, and the magnitude of the turn angle, the steering characteristic data can be constructed. For example, a large angular velocity lasting for a period of time means that the rail vehicle is making a large-angle turn.

[0050] In this embodiment, the vibration characteristic data can provide some position-related information of the rail vehicle during driving. For example, if a strong vibration at a specific frequency occurs at a certain position, the rail vehicle may have passed over a track joint or a specific defect position on the track. Combining the steering characteristic data, when the rail vehicle is turning, based on the changes in the steering angle and speed, the approximate path of the rail vehicle on the track can be inferred. Thus, the initial driving trajectory of the rail vehicle can be constructed.

[0051] In this embodiment, matching the driving trajectory of the rail vehicle with the track map to obtain the driving trajectory of the rail vehicle on the track map includes: comparing the geometric characteristics (such as curve shape, length, etc.) of the driving trajectory with the track segments in the track map, and at the same time combining the relevance of the vibration characteristic data and the steering characteristic data with the key nodes in the track map.

[0052] For example, if the vibration characteristics in the driving trajectory match a section of uneven track marked in the track map, and the steering characteristics also conform to the track direction in this area (such as passing through a known bend), the specific driving trajectory of the rail vehicle on the track map can be determined.

[0053] Exemplarily, assume there is a rail vehicle running on a complex section of track. After the acceleration data collected by its accelerometer is subjected to fast Fourier transform, an obvious peak with a relatively high amplitude is found at 50 Hz in the frequency domain. After judgment, this conforms to the periodic unevenness at a specific position of the track, indicating that the rail vehicle is traveling on this special track section. This is the position information brought by the vibration characteristic data. At the same time, the attitude angle change obtained by integrating the gyroscope data shows that the angular velocity rapidly increases and lasts for 5 seconds during a certain period, and the turning angle reaches 45 degrees, determining that the rail vehicle has performed a large-angle turning operation, and the turning characteristic data is extracted. By synthesizing these vibration and turning characteristic data, the driving trajectory of the rail vehicle is initially outlined. For example, it first passes through a straight section of track and then enters a curve. When this trajectory is matched with the track map, it is found that its geometric shape is similar to a certain section of track on the map, and the vibration characteristics correspond to the uneven track marked on the map, and the turning characteristics also fit the known curve, finally accurately determining the driving trajectory of the rail vehicle on the track map, achieving precise positioning and path tracking.

[0054] It can be concluded from the above that in this embodiment, by processing the acceleration data to obtain the vibration characteristic data, the vibration information can be used to reflect the track condition and the position correlation of the rail vehicle. For example, the position of the track defect can be determined based on specific vibrations, supplementing details for positioning. By processing the angular velocity data to obtain the turning characteristic data, the turning situation of the rail vehicle can be accurately captured, effectively tracking the change of the driving path. Based on the two to determine the driving trajectory, it does not rely on external complex positioning facilities and has strong adaptability in the tunnel environment. Finally, by matching with the track map, the positioning accuracy is further improved, and the position of the rail vehicle can be accurately locked in complex scenarios with multiple rails and turnouts, ensuring efficient and safe operation.

[0055] In an embodiment of the present disclosure, processing the acceleration data to obtain the vibration characteristic data of the rail vehicle includes:

[0056] Decompose the acceleration data to obtain the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction;

[0057] Integrate the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction to obtain the speed change curve of the rail vehicle;

[0058] Extract features from the speed change curve of the rail vehicle to obtain the vibration characteristic data of the rail vehicle.

[0059] In this embodiment, the acceleration component reflects the change in the speed magnitude of the rail vehicle, such as the acceleration and deceleration processes; the centrifugal component is related to the centripetal acceleration generated when the rail vehicle changes direction while traveling on a curve and can reflect the turning situation of the rail vehicle.

[0060] Establish an orbital coordinate system. The forward direction of the rail vehicle can be set as the orbital tangent direction, and the orbital tangent direction is set as the x-axis; the direction perpendicular to the orbital plane and upward is set as the z-axis; the y-axis is determined according to the right-hand rule. Based on the acceleration data, obtain the total acceleration vector, and decompose the total acceleration vector into the corresponding coordinate axis directions of the orbital coordinate system to obtain the acceleration component along the orbital tangent direction and the centrifugal component perpendicular to the orbital direction.

[0061] In this embodiment, integrate the acceleration component over time to obtain the velocity information of the rail vehicle changing with time along the orbital tangent direction; integrate the centrifugal component to obtain the change of the velocity component related to the direction change caused by turning over time. Based on the velocity information changing with time and the change of the velocity component related to the direction change over time, obtain the velocity change curve of the rail vehicle. The velocity change curve can intuitively display the velocity magnitude and the direction change trend of the rail vehicle at different times.

[0062] Exemplarily, assume that the acceleration component along the orbital tangent direction is , which represents a function of time. The initial velocity of the rail vehicle in this direction is . After time t, the velocity in the tangent direction can be obtained by integral calculation:

[0063]

[0064] Similarly, for the velocity component corresponding to the centrifugal component perpendicular to the orbital direction, a similar integral calculation method can also be adopted. Finally, combine the velocity components in each direction to obtain the velocity change curve of the rail vehicle.

[0065] In this embodiment, during the driving process of the rail vehicle, due to the influence of many factors such as the condition of the track itself, the interaction between the wheels and the track, and the characteristics of the vehicle's own mechanical structure, vibration phenomena will occur. The vibration phenomena can show certain regular characteristics on the velocity change curve, such as the velocity fluctuating periodically at certain frequencies, or having sudden changes at specific times, etc.

[0066] In this embodiment, the velocity change curve can be transformed from the time domain to the frequency domain through fast Fourier transform, and vibration characteristic data can be obtained based on the intensity distribution information of different frequency components in the frequency domain.

[0067] Exemplarily, it is found that there is an obvious peak at a specific frequency f in the frequency domain, and the amplitude corresponding to this peak is relatively large, indicating that the rail vehicle is affected by a fixed-period interference source during the driving process. These characteristic data are used to reflect the vibration situation of the rail vehicle.

[0068] As can be seen from the above, in this embodiment, by processing the acceleration data, the motion state of the rail vehicle can be accurately analyzed. Decomposing the acceleration can distinguish the tangential and vertical direction components, and clarify the influence of the speed magnitude and the acceleration related to turning. Integrating to obtain the speed change curve can visually present the evolution of the speed over time, covering acceleration, deceleration, and the change of the speed vector caused by turning. The vibration characteristic data extracted by the feature extraction can effectively reveal the vibration conditions of the rail vehicle caused by factors such as the track flatness and the wheel state, providing a key basis for accurately determining the driving trajectory of the rail vehicle on the track map. In addition, this embodiment can also judge the track conditions and predict the wear of the rail vehicle components through this method.

[0069] In an embodiment of the present disclosure, processing the angular velocity data to obtain the attitude angle characteristic data of the rail vehicle includes:

[0070] Decompose the angular velocity data to obtain the rotation component around the axis perpendicular to the track plane;

[0071] Integrate the rotation component around the axis perpendicular to the track plane to obtain the attitude angle change curve of the rail vehicle;

[0072] Extract features from the attitude angle change curve of the rail vehicle to obtain the steering characteristic data of the rail vehicle.

[0073] In this embodiment, the rotation component reflects the key information of the rail vehicle's steering and attitude change, and eliminates the interference brought by the rotation motion in other minor directions.

[0074] Based on the angular velocity data, an angular velocity vector is obtained, and the angular velocity vector is decomposed into the corresponding coordinate axis directions of the track coordinate system to obtain the rotation component around the axis perpendicular to the track plane (z-axis).

[0075] Integrate the rotation component over time to obtain the attitude angle change curve, that is, the change of the angle of the rail vehicle around the axis perpendicular to the track plane over time.

[0076] Exemplarily, let the rotation component around the axis perpendicular to the track plane be , which represents a function of time. Assume that the initial attitude angle of the rail vehicle around the axis perpendicular to the track plane is , after time t, the attitude angle can be obtained by integral calculation:

[0077]

[0078] Through continuous integral calculation, a complete attitude angle change curve can be plotted, clearly presenting the dynamic changes of the track vehicle's attitude. The attitude angle change curve reflects how the attitude angle of the track vehicle changes over time during driving, intuitively showing the process of attitude changes such as the track vehicle turning and maintaining straight driving.

[0079] In this embodiment, the steering characteristic data of the track vehicle can be obtained based on the slope of the attitude angle change curve.

[0080] Judge the slope of the attitude angle change curve (i.e., the rate of attitude angle change). If the slope in a certain time period is greater than the set value, it indicates that the track vehicle is passing through a turnout at the corresponding moment. Extract features by judging the slope of the attitude angle change curve, and then summarize and form the steering characteristic data, so as to accurately grasp the steering characteristics of the track vehicle.

[0081] It can be concluded from the above that in this embodiment, by decomposing the angular velocity data, it accurately focuses on the rotation component around the axis perpendicular to the track plane, excluding the interference of irrelevant information. Integrating to obtain the attitude angle change curve, intuitively presenting the dynamic process of the track vehicle turning, and reflecting the details of its direction change on the track. Then, through feature extraction, the steering characteristic data is obtained, which provides a basis for accurately judging the steering timing, angle and rate of the track vehicle, thereby effectively improving the accuracy of determining the driving trajectory and helping the track vehicle to accurately position in a complex environment.

[0082] In an embodiment of the present disclosure, it further includes:

[0083] Determine the motion state of the track vehicle based on the acceleration data. The motion state of the track vehicle includes uniform linear motion and non-uniform linear motion;

[0084] Determine the weights of the acceleration data and the angular velocity data based on the motion state of the track vehicle;

[0085] Perform weighted fusion on the acceleration data and the angular velocity data respectively to obtain the acceleration vector and the angular velocity vector respectively.

[0086] In this embodiment, integrating the accelerometer data to obtain the instantaneous velocity information of the track vehicle. Let the acceleration components measured by the accelerometer in the three coordinate axis directions of the above track coordinate system be 、 、 , the initial velocity is , and the velocity after time t can be calculated through the following integral formula in each axis direction:

[0087]

[0088]

[0089]

[0090] In response to within a set time window, the motion state of the rail vehicle is judged based on the acceleration change of the rail vehicle.

[0091] Exemplarily, a time window length is set to T, and the change amount of the speed component within this time period is checked every time T. 、 、 。If the following conditions are met 、 、 (where is a set very small speed change threshold, which can be determined according to the actual running speed accuracy requirement of the rail vehicle), it is preliminarily judged that the rail vehicle is in a uniform motion state.

[0092] Further combining with the position information of the rail vehicle, if the position change is basically along the track straight line direction in this uniform motion state, that is, the change of the component of the displacement in the direction perpendicular to the track is extremely small, it is finally determined that the rail vehicle is in a uniform linear motion state; otherwise, it is judged as a non-uniform linear motion state, and the non-uniform linear motion state can be a motion state such as acceleration, deceleration or turning.

[0093] In this embodiment, when the motion state is a uniform linear motion state, the weight of the acceleration data is set to correspondingly, and the weight of the angular velocity data is set to where 。

[0094] For example, when the motion state of the rail vehicle is a uniform linear motion state , ,in this way, it is possible to mainly rely on the data detected by the angular velocity sensor to determine the attitude of the rail vehicle. Because during uniform linear motion, most of the data measured by the acceleration sensor is noise or small interference, reducing its weight can reduce the adverse impact on attitude determination.

[0095] When the motion state of the rail vehicle is a non-uniform linear motion state, it is further judged whether it is an acceleration or deceleration situation. It can be determined by observing the change trend of the speed component. For example, if the speed component continuously increases in several consecutive time windows and the acceleration value is greater than a set acceleration threshold ,it is judged as the acceleration stage; if the speed component continuously decreases and the acceleration value is less than the set deceleration threshold, it is judged as the deceleration stage. During the acceleration or deceleration stage, the weight of the accelerometer data can be increased. For example, if is set, then , making it possible to make better use of accelerometer data to accurately capture changes in the speed of the railcar, assisting in more accurately determining the motion state of the railcar and subsequent trajectory calculation.

[0096] In this embodiment, the initial acceleration vector measured by the acceleration sensor is assumed to be , the angular velocity vector measured by the angular velocity sensor is .

[0097] The obtained acceleration data weight is , the angular velocity data weight is , then the fused data vector used to describe the motion state of the railcar can be calculated by the following weighted average method:

[0098]

[0099] in, is the fused acceleration vector, is the acceleration vector after fusion at the previous moment. This takes into account the continuity of historical data and avoids sudden changes in the fusion results.

[0100]

[0101] in, is the fused angular velocity vector, is the angular velocity vector after fusion at the previous moment.

[0102] From the above, it can be concluded that this embodiment determines the weights of acceleration and angular velocity data and performs weighted fusion by judging the motion state of the rail vehicle based on acceleration data, which can effectively reduce the noise interference of acceleration data during uniform linear motion and accurately determine the posture; during non-uniform linear motion, the weight of acceleration data is reasonably increased to capture speed changes, improve the accuracy of motion state and trajectory calculation, make rail vehicle positioning and motion analysis more reliable, and ensure its safety and efficiency in track operation.

[0103] In one embodiment of the present disclosure, it further includes:

[0104] Calculating the distance traveled by the railcar based on the rotation of its wheels;

[0105] The position of the railcar is calibrated based on the distance the railcar has traveled.

[0106] In this embodiment, there may be certain measurement deviations when the acceleration sensor measures acceleration. When calculating velocity and displacement through integration, these deviations will accumulate over time, resulting in a large deviation between the calculated position of the rail vehicle and the actual position. During a long-term detection process, these deviations will accumulate, thus affecting the positioning accuracy of the rail vehicle. Therefore, in this embodiment, the traveling distance of the rail vehicle can be calculated based on the rotation of the wheels, and the determined position of the rail vehicle can be calibrated based on the traveling distance of the rail vehicle to improve the accuracy of position determination.

[0107] In this embodiment, the change in the optical signal during the rotation of the wheels can be detected by an optical encoder to determine the rotation angle, and the traveling distance of the rail vehicle can be determined based on the rotation angle.

[0108] Exemplarily, the wheels of the rail vehicle roll on the track. Every time the wheel rotates one circle, the rail vehicle will advance a fixed distance on the track, and this distance is directly related to the circumference of the wheel. If the radius of the wheel is known as r, according to the circumference formula of a circle C = 2πr, every time the wheel rotates one circle, the rail vehicle will travel a distance of 2πr along the track. By installing an optical encoder at the wheel to record the number of rotations n of the wheel, the traveling distance s of the rail vehicle can be calculated through the formula s = 2πrn.

[0109] In this embodiment, based on the initial known position of the rail vehicle, as the rail vehicle runs, after the rail vehicle reaches a key node, the position of the rail vehicle is updated according to the calculated traveling distance of the wheel rotation.

[0110] From the above, it can be concluded that in this embodiment, the traveling distance is calculated based on the wheel rotation, and relatively stable displacement information of the rail vehicle can be directly obtained. Calibrating the position with this can effectively compensate for the position deviation problem caused by error accumulation when only relying on jerk data and angular velocity data for positioning. It not only greatly improves the accuracy of determining the position of the rail vehicle, but also provides a reliable guarantee for the safe driving, precise dispatching of the rail vehicle, and accurate positioning on the track map.

[0111] In an embodiment of the present disclosure, calibrating the position of the rail vehicle based on the traveling distance of the rail vehicle includes:

[0112] Fusing the acceleration data and angular velocity data of the rail vehicle with the traveling distance of the rail vehicle to obtain a position correction value of the rail vehicle;

[0113] Calibrating the position of the rail vehicle based on the position correction value.

[0114] In this embodiment, the acceleration data and angular velocity data of the rail vehicle are mainly obtained through acceleration sensors and angular acceleration sensors. Based on these data, information such as the speed, displacement, and attitude change of the rail vehicle can be obtained, and then the position of the rail vehicle can be determined. However, during the calculation process, due to the measurement errors of the sensors themselves and the continuous accumulation of these errors over time due to integral operations, there is a deviation between the calculated position and the actual position. The driving distance calculated through the rotation of the wheels is relatively more direct and accurate. By fusing it with the acceleration and angular velocity data, the advantages of all aspects can be integrated to obtain a more accurate position correction value.

[0115] In this embodiment, a state equation can be constructed based on the acceleration data and angular velocity data to obtain the state of the rail vehicle at the current moment.

[0116] Taking the position, speed, attitude angle, etc. of the rail vehicle as state variables and the acceleration data and angular velocity data as input quantities to participate in the equation to reflect the influence on the state change.

[0117] Taking the driving distance calculated based on the rotation of the wheels as the observed value, an observation equation is established.

[0118] The observation equation describes the relationship between the observed value (driving distance) and the state variables (such as the position, speed, attitude angle, etc. of the rail vehicle).

[0119] Based on the state of the rail vehicle at the previous moment, the state at the current moment, the observed value, and the observation equation, the predicted state is corrected according to the set weight to obtain the fused position correction value.

[0120] Exemplarily, it is defined that the state vector X includes the position coordinates x, y of the rail vehicle, the velocity components along the x-axis and y-axis directions , and the attitude angle , that is .

[0121] When the rail vehicle starts, the initial position coordinates are known as , the initial velocities in the x-axis and y-axis directions are respectively , , the initial attitude angle is , and the initial state vector .

[0122] Considering factors such as measurement errors in acceleration sensors and angular velocity sensors, a noise covariance matrix Q is set to describe the uncertainty of the sensors themselves. At the same time, since there may be certain errors in calculating the driving distance based on wheel rotation, an observation noise covariance matrix R is set to characterize the uncertainty of the observation. The specific element values in the covariance matrix Q and the covariance matrix R can be determined by conducting accuracy tests and experimental analyses on each sensor in advance.

[0123] The state equation is:

[0124]

[0125] Where, is the state vector at time; is the state transition matrix, representing the change relationship of the state variable from time k to time; is the control input matrix. The acceleration data and angular velocity data are used as control inputs, and their element values are determined according to their action relationship with the state variable; is the control input vector, which includes the acceleration components measured by the accelerometer in the x and y axes , and the angular velocity ; is the system noise vector, whose mean value is zero and the covariance matrix is the above-set Q, used to simulate the influence of various uncertainty factors existing in the system on the state change.

[0126] The observation equation is:

[0127]

[0128] Where, is the observation vector at time, here referring to the driving distance s; is the observation matrix, representing the relationship between the state variable and the observation value.

[0129] Based on the state estimate at the previous time ( time), the state at the current time (k time) is predicted using the state equation:

[0130]

[0131] At the same time, the covariance matrix of the predicted state is calculated:

[0132]

[0133] Where, It is the covariance matrix of the state estimate at the previous moment. Through these calculations, we can get a priori estimate of the state at the current moment when it is not combined with the current observation value.

[0134] Calculate Kalman gain , Kalman gain Determines the weight given to observations and predictions during fusion. The calculation formula is:

[0135]

[0136] Use Kalman gain to combine current observations Forecast status Update to get the fused current state estimate :

[0137]

[0138] Finally, update the covariance matrix of the state estimate :

[0139]

[0140] in, is the identity matrix.

[0141] After the above-mentioned repeated prediction and update steps, the state of the railcar is dynamically fused and calculated based on the newly acquired acceleration, angular velocity data and the travel distance calculated by wheel rotation. The position coordinate component in is the fused position correction value, which can be used for subsequent calibration of the rail vehicle position to make its position estimate closer to the actual position.

[0142] For example, at a certain moment, after calculation, the predicted railcar position coordinates are (10.2, 5.1) (unit: meter). The position correction values obtained after Kalman filter fusion are +0.3 meters in the x-direction and -0.1 meters in the y-direction. The calibrated position coordinates become (10.5, 5.0) meters. Through continuous fusion and calibration, the accuracy of the railcar position is guaranteed.

[0143] As can be seen from the above, this embodiment integrates the railcar's acceleration and angular velocity data with travel distance to calibrate position. This effectively compensates for the deviation caused by accumulated sensor errors when relying solely on acceleration and angular velocity to infer position, integrating the advantages of multiple data sources. Through Kalman filtering, precise fusion and dynamic position correction improve positioning accuracy and reliability.

[0144] In one embodiment of the present disclosure, constructing a track map includes:

[0145] Based on the spatial distribution of the point cloud data corresponding to the track, the center line of the track is obtained;

[0146] Based on the center line of the track and the geometric features of the track, a track map is constructed.

[0147] In this embodiment, the tunnel environment is scanned by a lidar to obtain the point cloud data of the tunnel environment; the point cloud data corresponding to the track contains the three-dimensional spatial information of the track, reflecting the actual shape of the track and the relative position relationship with the surrounding environment.

[0148] The point cloud data of the tunnel environment is subjected to clustering processing to separate the points belonging to the track part from the points in the surrounding environment, and the point cloud data corresponding to the track is obtained.

[0149] By identifying the geometric features such as the trend and curvature change of the point cloud data corresponding to the track in space, the extension direction of the track is obtained, and the key points reflecting the trend of the track center axis are found.

[0150] Based on the identified key points, a smoothing curve is constructed using a curve fitting algorithm, which is the center line of the track. The smoothing curve can abstractly represent the main trend of the track in space, ignoring the tiny unevenness on the track surface and other details, and providing a core reference line for the subsequent construction of the track map.

[0151] In this embodiment, the curvature of each section of the track is marked at the corresponding position of the center line, indicating where the curve is and the degree of curvature of the curve; the turnout positions are clearly marked to clarify the branch situation and connection relationship of the track. The track map constructed in this way can completely present the whole picture of the track, providing an accurate reference for applications such as the positioning, navigation and driving trajectory matching of the rail vehicle, and helping to accurately grasp the position and driving state of the rail vehicle in the entire track network.

[0152] In an embodiment of the present disclosure, based on the distance between the rail vehicle and the target key node, the first reference data is obtained, and the target key node is the key node closest to the rail vehicle during the driving process of the rail vehicle;

[0153] Based on the second reference data, the position of the rail vehicle is calibrated.

[0154] In practical applications, due to the complex environment of tunnel construction, power outages may occur. When the rail vehicle encounters a power outage fault in the tunnel, it will not be able to normally obtain the acceleration data and angular velocity data of the rail vehicle, and the rail vehicle will stop operating. However, affected by uncontrollable factors, the rail vehicle may shift on the track when it stops operating, resulting in an error in the positioning of the rail vehicle when the power supply is normal. Therefore, this embodiment can calibrate the shift caused by the power outage.

[0155] In this embodiment, first, when the rail vehicle is running normally, continuously monitor and record the distance information between it and the nearest key node (such as a specific track identification point, turnout point, etc.), and store the obtained distance information in real time. Once a power failure occurs, the distance between the rail vehicle and the target key node can be immediately recorded, that is, the first reference data is obtained. During the power failure, the rail vehicle may deviate on the track due to various factors.

[0156] When the power supply is restored, the acceleration sensor and the angular velocity sensor start working again. At this time, the distance between the rail vehicle and the previously recorded target key node is obtained again to form the second reference data. If the position of the rail vehicle has deviated, there will be a deviation between the distance data of the rail vehicle and the target key node obtained before and after.

[0157] By calculating the deviation value between the first reference data and the second reference data, the displacement change of the rail vehicle during the power failure can be inferred. Based on this deviation, the current position of the rail vehicle is calibrated to correct the positioning error caused by the deviation during the power failure.

[0158] Exemplarily, if the first reference data shows that the distance from the key node is 10 meters during the power failure and the second reference data is 10.5 meters after the power supply is restored, it means that the rail vehicle has deviated 0.5 meters away from the key node. Then, the position coordinates of the rail vehicle can be adjusted accordingly to ensure the accuracy of the rail vehicle positioning, so that it can continue to operate safely and efficiently based on the correct position information after the power supply is restored.

[0159] It can be concluded from the above that in this embodiment, the first reference data is obtained by recording the distance between the rail vehicle and the target key node, and the second reference data is obtained after the power supply is restored and the position is calibrated accordingly, effectively solving the positioning error problem caused by the deviation of the rail vehicle during the power failure in complex environments such as tunnel construction. Without relying on complex sensor fusion or map matching algorithms, only using the distance information of the key node can accurately correct the position, ensuring the continuity and safety of the rail vehicle operation and improving the operation management efficiency.

[0160] Corresponding to the rail vehicle positioning method in the above embodiment, Figure 2 is the structural block diagram of the rail vehicle positioning device provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 and the rail vehicle positioning device 20 includes: a track map construction module 21, a driving trajectory generation module 22, and a positioning module 23.

[0161] Among them, the track map construction module 21 is used to construct a track map;

[0162] The driving trajectory generation module 22 is used to determine the driving trajectory of the rail vehicle on the track map based on the acceleration data and angular velocity data of the rail vehicle;

[0163] A positioning module 23 for determining the position of the rail vehicle based on the driving track of the rail vehicle on the track map.

[0164] In an embodiment of the present disclosure, the driving track generation module 22 is further specifically configured to:

[0165] Process the acceleration data to obtain the vibration characteristic data of the rail vehicle;

[0166] Process the angular velocity data to obtain the steering characteristic data of the rail vehicle;

[0167] Determine the driving track of the rail vehicle based on the vibration characteristic data and the steering characteristic data;

[0168] Match the driving track of the rail vehicle with the track map to obtain the driving track of the rail vehicle on the track map.

[0169] In an embodiment of the present disclosure, the driving track generation module 22 is further specifically configured to:

[0170] Decompose the acceleration data to obtain the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction;

[0171] Integrate the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction to obtain the speed change curve of the rail vehicle;

[0172] Extract the characteristics of the speed change curve of the rail vehicle to obtain the vibration characteristic data of the rail vehicle.

[0173] In an embodiment of the present disclosure, the driving track generation module 22 is further specifically configured to:

[0174] Decompose the angular velocity data to obtain the rotation component around the axis perpendicular to the track plane;

[0175] Integrate the rotation component around the axis perpendicular to the track plane to obtain the attitude angle change curve of the rail vehicle;

[0176] Extract the characteristics of the attitude angle change curve of the rail vehicle to obtain the steering characteristic data of the rail vehicle.

[0177] In an embodiment of the present disclosure, the rail vehicle positioning device 20 further includes: a calibration module;

[0178] The calibration module is specifically configured to:

[0179] Calculate the driving distance of the rail vehicle based on the wheel rotation of the rail vehicle;

[0180] Calibrate the position of the rail vehicle based on the driving distance of the rail vehicle.

[0181] In one embodiment of the present disclosure, the calibration module is further specifically configured to:

[0182] Fuse the acceleration data and angular velocity data of the rail vehicle with the traveling distance of the rail vehicle to obtain a position correction value of the rail vehicle;

[0183] Calibrate the position of the rail vehicle based on the position correction value.

[0184] In one embodiment of the present disclosure, the rail map construction module 21 is specifically configured to:

[0185] Obtain the center line of the rail based on the spatial distribution of the point cloud data corresponding to the rail;

[0186] Construct a rail map based on the center line of the rail and the geometric features of the rail.

[0187] See Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module in the above-mentioned device embodiments, such as Figure 2 the functions of the modules 21 to 22 shown.

[0188] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (Central Processing Unit, CPU), and this processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0189] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the orientation information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0190] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0191] In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may implement the implementation manners described in the first and second embodiments of the rail vehicle positioning method provided by the embodiments of the present disclosure, and may also implement the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0192] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It may also be completed by instructing relevant hardware through the computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments may be implemented. Among them, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0193] The computer-readable storage medium may be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store the data that has been output or will be output.

[0194] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0195] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0196] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces or units, or can also be electrical, mechanical, or other forms of connections.

[0197] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can also be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this disclosure.

[0198] In addition, the functional units in each embodiment of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0199] The above is only the specific implementation manner of this disclosure, but the protection scope of this disclosure is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope disclosed by this disclosure, and these modifications or substitutions should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be subject to the protection scope of the claims.

Claims

1. A railcar positioning method, characterized in that: include: Construct track maps; Decompose the acceleration data to obtain the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction; Integrating the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction to obtain a speed change curve of the railcar; Extracting features from a speed variation curve of the railcar to obtain vibration feature data of the railcar; The angular velocity data is decomposed to obtain the rotation component around the axis perpendicular to the orbital plane; Integrate the rotation component around the axis perpendicular to the track plane to obtain the attitude angle change curve of the railcar; Extracting features of the attitude angle change curve of the railcar to obtain steering feature data of the railcar; determining a travel trajectory of the railcar based on the vibration characteristic data and the steering characteristic data; Matching the travel trajectory of the railcar with the rail map to obtain the travel trajectory of the railcar on the rail map; determining a position of the railcar based on a travel trajectory of the railcar on a rail map; The method further comprises: When the railcar encounters a power failure in the tunnel, first reference data is obtained based on the distance between the railcar and a target key node, where the target key node is the key node closest to the railcar during its travel; When power supply is restored, the distance between the rail vehicle and the target key node is obtained to form second reference data; The position of the railcar is calibrated based on the second reference data.

2. The railcar positioning method according to claim 1, wherein: Also includes: calculating a travel distance of the railcar based on wheel rotations of the railcar; The position of the railcar is calibrated based on the distance the railcar has traveled.

3. The rail vehicle positioning method according to claim 2, wherein: The calibrating the position of the railcar based on the travel distance of the railcar includes: fusing the acceleration data and angular velocity data of the railcar with the travel distance of the railcar to obtain a position correction value of the railcar; The position of the railcar is calibrated based on the position correction value.

4. The railcar positioning method according to claim 1, wherein: The constructing of the track map includes: Based on the spatial distribution of the point cloud data corresponding to the track, the center line of the track is obtained; A track map is constructed based on the centerline of the track and geometric features of the track.

5. A railcar positioning device, characterized in that: include: Track map construction module, used to construct track maps; The driving trajectory generation module decomposes the acceleration data to obtain the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction; Integrating the acceleration component along the track tangent direction and the centrifugal component perpendicular to the track direction to obtain a speed change curve of the railcar; Extracting features from a speed variation curve of the railcar to obtain vibration feature data of the railcar; The angular velocity data is decomposed to obtain the rotation component around the axis perpendicular to the orbital plane; Integrate the rotation component around the axis perpendicular to the track plane to obtain the attitude angle change curve of the railcar; Extracting features of the attitude angle change curve of the railcar to obtain steering feature data of the railcar; determining a travel trajectory of the railcar based on the vibration characteristic data and the steering characteristic data; Matching the travel trajectory of the railcar with the rail map to obtain the travel trajectory of the railcar on the rail map; a positioning module, configured to determine a position of the rail vehicle based on a travel trajectory of the rail vehicle on a rail map; Calibration modules for: When the railcar encounters a power failure in the tunnel, first reference data is obtained based on the distance between the railcar and a target key node, where the target key node is the key node closest to the railcar during its travel; When power supply is restored, the distance between the rail vehicle and the target key node is obtained to form second reference data; The position of the railcar is calibrated based on the second reference data.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images